{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 60.0,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 10.0,
      "grad_norm": 1.9736052751541138,
      "learning_rate": 0.00018181818181818183,
      "loss": 2.5512,
      "step": 10
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.2568399906158447,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.0932,
      "step": 20
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.03556245192885399,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.0337,
      "step": 30
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.036208294332027435,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.0326,
      "step": 40
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.0230406541377306,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.0323,
      "step": 50
    },
    {
      "epoch": 60.0,
      "grad_norm": 0.012407252565026283,
      "learning_rate": 0.0,
      "loss": 0.0322,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 60,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 503074201681920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}